Long-context retrieval
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
76.4Accuracy
12
Jun 11, 2026
90.6Accuracy
12
Jun 11, 2026
97Accuracy
12
Jun 11, 2026
98.6Accuracy
12
Jun 11, 2026
93.4Accuracy
12
Jun 11, 2026
97Accuracy
12
Jun 11, 2026
100Accuracy
12
Jun 11, 2026
99.8Accuracy
12
Jun 11, 2026
100Accuracy
12
Jun 11, 2026
100Accuracy
12
Jun 11, 2026
100Accuracy
12
Jun 11, 2026
100Accuracy
12
Jun 11, 2026
99.6Exact Match Accuracy
12
May 8, 2026
92.97Score
12
May 28, 2026
71.5nDCG@10
11
Jun 23, 2026
0.783nDCG@10
11
Jun 23, 2026
100Accuracy (Single)
10
Jun 24, 2026
96Accuracy (Single)
10
Jun 24, 2026
0.813nDCG@10
9
Jun 23, 2026
98.1nDCG@10
9
Jun 23, 2026
96.5nDCG@10
9
Jun 23, 2026
97.2Accuracy
9
May 19, 2026
98.8Accuracy
9
May 19, 2026
100Accuracy
9
May 19, 2026
100Accuracy
9
May 19, 2026